# MiMo-V2.5 vs Qwen2.5-VL 72B Instruct

> MiMo-V2.5 is the stronger model overall, scoring 43.0 to 29.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mimo-v2-5-vs-qwen2-5-vl-72b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. MiMo-V2.5 scores higher in 2 categories and Qwen2.5-VL 72B Instruct in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.5 leads 27.8 to 20.0.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $2.80 / $8.40 for Qwen2.5-VL 72B Instruct.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 131K.

## Snapshot

| | MiMo-V2.5 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 43.0 | 29.4 |
| Rank | 89 | 298 |
| Context | 1.05M | 131K |
| Input $/M | $0.14 | $2.80 |
| Output $/M | $0.28 | $8.40 |
| Weights | Open | Open |

## Coding

- MiMo-V2.5: 43.6 (#75)
- Qwen2.5-VL 72B Instruct: —

| Benchmark | MiMo-V2.5 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena WebDev | 1438 | — |
| SciCode | 43.1% | — |
| LMArena Coding | 1469 | — |
| ALE-Bench | 513.95 | — |

## Agentic & Tool Use

- MiMo-V2.5: —
- Qwen2.5-VL 72B Instruct: 18.4 (#136)

| Benchmark | MiMo-V2.5 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| OSWorld | — | 5% |

## Reasoning

- MiMo-V2.5: 27.8 (#98)
- Qwen2.5-VL 72B Instruct: 20.0 (#228)

| Benchmark | MiMo-V2.5 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Kagi LLM Benchmark | — | 36% |
| CritPt | 3.7% | — |
| LMArena Hard Prompts | 1450 | — |

## Math

- MiMo-V2.5: 35.4 (#145)
- Qwen2.5-VL 72B Instruct: —

| Benchmark | MiMo-V2.5 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| ProofBench | 16% | — |
| LMArena Math | 1436 | — |

## Knowledge

- MiMo-V2.5: 40.2 (#109)
- Qwen2.5-VL 72B Instruct: —

| Benchmark | MiMo-V2.5 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Expert | 1459 | — |

## Multimodal

- MiMo-V2.5: 39.0 (#53)
- Qwen2.5-VL 72B Instruct: 32.9 (#92)

| Benchmark | MiMo-V2.5 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Vision | 1245 | 1107 |
| Video-MME | — | 73.5% |
| GeoBench | — | 62% |
| SpatialViz-Bench | — | 33.3% |

## Multilingual

- MiMo-V2.5: 52.0 (#96)
- Qwen2.5-VL 72B Instruct: —

| Benchmark | MiMo-V2.5 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Non-English | 1404 | — |
| LMArena Chinese | 1467 | — |
| LMArena French | 1447 | — |
| LMArena German | 1421 | — |
| LMArena Japanese | 1304 | — |
| LMArena Korean | 1363 | — |
| LMArena Russian | 1395 | — |
| LMArena Spanish | 1412 | — |

## Instruction Following

- MiMo-V2.5: 75.7 (#55)
- Qwen2.5-VL 72B Instruct: —

| Benchmark | MiMo-V2.5 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1433 | — |

## Long Context

- MiMo-V2.5: 44.1 (#69)
- Qwen2.5-VL 72B Instruct: —

| Benchmark | MiMo-V2.5 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1444 | — |

## Writing & Preference

- MiMo-V2.5: 61.8 (#82)
- Qwen2.5-VL 72B Instruct: —

| Benchmark | MiMo-V2.5 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Text | 1427 | — |
| LMArena Creative Writing | 1392 | — |
| LMArena Multi-Turn | 1445 | — |

## FAQ

### Is MiMo-V2.5 better than Qwen2.5-VL 72B Instruct?

MiMo-V2.5 is the stronger model overall, scoring 43.0 to 29.4 on the Noometry Index.

### Which is cheaper, MiMo-V2.5 or Qwen2.5-VL 72B Instruct?

MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Qwen2.5-VL 72B Instruct lists at $2.80 and $8.40.

### Which has the bigger context window?

MiMo-V2.5 does, with 1.05M tokens against 131K.

### How many benchmarks do MiMo-V2.5 and Qwen2.5-VL 72B Instruct share?

1 benchmark has published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Qwen2.5-VL 72B Instruct has 6.